A Novel Spatio-Temporal 3D Convolutional Encoder-Decoder Network for Dynamic Saliency Prediction

As human beings are living in an always changing environment, predicting saliency maps from dynamic visual stimulus is of importance for modeling human visual system. Compared with human behavior, recent models based on LSTM and 3DCNN are still not good enough due to the limitation in spatio-tempora...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	IEEE access Ročník 9; s. 1
Hlavní autori:	Li, Hao, Qi, Fei, Shi, Guangming
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Piscataway IEEE 01.01.2021 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:	3D Fully Convolutional Networks Changing environments Coders Computational modeling Correlation coefficients Decoding Dynamic Saliency Prediction Encoders-Decoders Feature extraction Predictions Predictive models Salience Solid modeling Spatio-Temporal Features Three-dimensional displays Visual Attention Visual stimuli Visualization
ISSN:	2169-3536, 2169-3536
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Buďte prvý, kto okomentuje tento záznam!